Update zAI endpoint and subscription details

.changeset/great-jars-flow.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Update zAI endpoint, subscription plans, and usage details

docs/provider-config/zai.mdx

@@ -56,16 +56,23 @@ Z AI offers subscription plans specifically designed for coding applications. Th
 #### Plan Options
 
 **GLM Coding Lite** - $3/month
-- 120 prompts per 5-hour cycle
-- Access to GLM-4.5 model
+- Powered by GLM-4.5
+- Up to ~120 prompts every 5 hours (about 3× the usage quota of the Claude Pro plan)
 - Works exclusively through coding tools like Cline
 
-**GLM Coding Pro** - $15/month  
-- 600 prompts per 5-hour cycle
-- Access to GLM-4.5 model
-- Works exclusively through coding tools like Cline
+**GLM Coding Pro** - $15/month
+- All Lite plan benefits
+- 5× Lite plan usage (~600 prompts every 5 hours, about 3× the usage quota of the Claude Max (5x) plan)
+- 40%–60% faster compared to Lite
+- Built-in image & video understanding and web search MCP
 
-Both plans offer promotional pricing for the first month: Lite drops from \$6 to \$3, Pro drops from \$30 to \$15.
+**GLM Coding Max** - $30/month
+- All Pro plan benefits
+- 4× Pro plan usage (~2400 prompts every 5 hours)
+- Guaranteed peak-hour performance
+- Early access to new features
+
+All plans offer promotional pricing for the first month: Lite drops from $6 to $3, Pro drops from $30 to $15, and Max drops from $60 to $30.
 
 <Frame>
   <img src="https://storage.googleapis.com/cline_public_images/docs/assets/zAI-coding-plan.png" alt="zAI subscription page showing GLM Coding Lite and Pro plans with pricing" />
@@ -85,6 +92,14 @@ To use the GLM Coding Plans with Cline:
   <img src="https://storage.googleapis.com/cline_public_images/docs/assets/zAI-provider.png" alt="Cline settings with zAI provider selected and API key field highlighted" />
 </Frame>
 
+#### Usage Details
+
+In terms of token consumption, each prompt typically allows 15–20 model calls, giving a total monthly allowance of tens of billions of tokens — all at only ~1% of standard API pricing, making it extremely cost-effective.
+
+Once subscribed, GLM-4.5 is automatically available in the supported tools using your plan's quota—no additional configuration required. If the quota is exhausted, it will automatically reset at the start of the next 5-hour cycle. The system will not consume other resource packs or account balance. Users with a Coding Plan can only use the plan's quota in supported tools and cannot call the model separately via API.
+
+**Note:** API calls are billed separately and do not use the Coding Plan quota. Please refer to the API pricing for details.
+
 The setup connects your subscription directly to Cline, giving you access to GLM-4.5's tool-calling capabilities optimized for coding workflows.
 
 ### Z AI's Hybrid Intelligence

src/core/api/providers/zai.ts

@@ -39,7 +39,9 @@ export class ZAiHandler implements ApiHandler {
 			}
 			try {
 				this.client = new OpenAI({
-					baseURL: this.useChinaApi() ? "https://open.bigmodel.cn/api/paas/v4" : "https://api.z.ai/api/paas/v4",
+					baseURL: this.useChinaApi()
+						? "https://open.bigmodel.cn/api/coding/paas/v4"
+						: "https://api.z.ai/api/coding/paas/v4",
 					apiKey: this.options.zaiApiKey,
 					defaultHeaders: {
 						"HTTP-Referer": "https://cline.bot",